Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate movement or transitions, particularly using "up" and "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    witter
    -0.17
    esser
    -0.16
    ess
    -0.16
    esses
    -0.16
    essor
    -0.15
    ocracy
    -0.15
     Tomáš
    -0.15
    igner
    -0.14
    ab
    -0.14
    umpt
    -0.14
    POSITIVE LOGITS
    pone
    0.15
    .maven
    0.14
    би
    0.14
    odium
    0.14
    backs
    0.14
    etty
    0.14
     Laz
    0.14
    isci
    0.14
    港
    0.13
    /stdc
    0.13
    Act Density 0.045%

    No Known Activations